In hybrid cloud model, organizations can keep their sensitive information and critical applications in the private cloud and move other data and applications to a public cloud, if necessary. To maintain data privacy i...
详细信息
ISBN:
(纸本)9781509019618
In hybrid cloud model, organizations can keep their sensitive information and critical applications in the private cloud and move other data and applications to a public cloud, if necessary. To maintain data privacy in workflow applications, we present a budget constrained hybrid cloud scheduler (BCHCS) which is a static heuristic scheduling algorithm. It is able to make decisions about scheduling sensitive tasks on private cloud and uses public cloud's resources for non-sensitive tasks, such that the makespan is minimized, while the budget limitation imposed by the user is satisfied. Experimental results show that the proposed method guarantees the execution of sensitive tasks on private cloud while achieving at least 7 percent lower makespan and higher success rate in comparison to similar existing techniques.
The increasing scale of multi-core processors are likely to be randomly heterogeneous by design or because of diversity and flaws. The latter type of heterogeneity introduced by some unforeseen variable factors such a...
详细信息
ISBN:
(纸本)9781509040933
The increasing scale of multi-core processors are likely to be randomly heterogeneous by design or because of diversity and flaws. The latter type of heterogeneity introduced by some unforeseen variable factors such as the manufacturing process variation is especially challenging because of its unpredictability. In this environment, thread scheduler and global power manager must handle such randomly heterogeneous. Furthermore, these algorithms must supply high efficiency, scalability and low overhead because future multi-core processors may have a number of cores on a single die. This paper presents a variationaware scheduling algorithm for application scheduling and power management. Thread switching and sampling among different cores in the multi-core processor introduce obvious overhead than previous many-core scheduling algorithms. Proposed scheme records the information of swapped thread of preferential core and uses tabu search-based randomly heterogeneous scheduling algorithm(TSR) to avoid the occurrence of repeated sampling and reduce the migration frequency and sampling frequency of a thread. The experimental results show that TSR algorithm has decreased 45.7% of thread migration and 42.2% of the sampling time as compared with local search algorithm. This paper regards the transcendental Hungarian offline scheduling algorithm as the baseline. ED2 of TSR only decrease by 8.58% as compared with that of Hungarian offline scheduling algorithm, but compared with the random search scheduling algorithm, ED2 of TSR decreased by 39.4%.
作者：
Zhao, TongJing, MeiHunan Normal Univ
Performance Comp & Stochast Informat Proc Minist Coll Math & Comp Sci Changsha 410081 Hunan Peoples R China
Task scheduling is an important component of parallel and distributed computing. Therefore, it is of theoretical significance and practical value to develop an effective task scheduling algorithm and implement it. For...
详细信息
Task scheduling is an important component of parallel and distributed computing. Therefore, it is of theoretical significance and practical value to develop an effective task scheduling algorithm and implement it. For the task scheduling in cloud computing environment, it means that a group of tasks consisting a working load are distributed to a number of computational nodes as per certain implementing time sequence based on scheduling discipline and strategy to short the time needed by the whole task scheduling and to achieve good implementation performance. Divisible task scheduling is one of the important roles in the parallel computation and distributed computation. In this paper, we studies on a classical algorithm: Uniform Multi-Round (UMR), based on which an improved multi-path divisible task scheduling algorithm: MSUMR (Master Service Uniform Multi-Round) algorithm is proposed. Such an algorithm could not only ensure the scheduling efficiency when the bandwidth is sufficient but also maximizes the computing efficiency of working node when the available bandwidth is limited. According to the experimental result, this algorithm, compared with such scheduling algorithms as UMR, Multi Installment (MI) and eXtended Multi-Installment (XMI), is improved in the two aspects of dividing algorithm and task allocation principles, thus short down the number of unused computing nodes during task implementation and making full use of computing resources, indicating batter practical application value.
In recent years cloud services have gained much attention as a result of their availability, scalability, and low cost. One use of these services has been for the execution of scientific workflows as part of Big Data ...
详细信息
ISBN:
(纸本)9781509036820
In recent years cloud services have gained much attention as a result of their availability, scalability, and low cost. One use of these services has been for the execution of scientific workflows as part of Big Data Analytics, which are employed in a diverse range of fields including astronomy, physics, seismology, and bioinformatics. There has been much research on heuristic scheduling algorithms for these workflows due to the problem's inherent complexity, however existing work has mainly considered execution in a utility grid environment using a generic distributed framework. For our research, we consider the ever-increasingly popular Apache Hadoop framework for scheduling workflow onto resources rented from cloud service providers. Contrary to other distributed frameworks, the Hadoop MapReduce model imposes a functional style onto application definition, and as such presents an interesting and unapproached challenge for workflow scheduling. Investigated in our work is budget-constrained workflow scheduling on the Hadoop MapReduce platform, wherein we devise both an optimal and a heuristic approach to minimize workflow makespan while satisfying a given budget constraint. We have implemented modifications to the Apache Hadoop framework to allow fully integrated workflow scheduling. These modifications are novel and have led to the completion of the first generic workflow scheduler fully integrated with the Apache Hadoop framework. Both the framework modifications and the proposed scheduler implementation have been extensively tested via execution on multiple workflow applications, which demonstrates the ability of our implementation to handle all possible workflow substructures. Results from our empirical studies further establish these facts.
As a distributed computing framework based on memory, Spark is being used by more and more enterprises. Generally, Spark runs in multi-user and multi-job mode, where may exist a large number of reuse of jobs. This reu...
详细信息
ISBN:
(纸本)9781509011926
As a distributed computing framework based on memory, Spark is being used by more and more enterprises. Generally, Spark runs in multi-user and multi-job mode, where may exist a large number of reuse of jobs. This reuse, here, refers to the calculation reuse inside the jobs, and it can greatly shorten the executing time of jobs in Spark. Therefore, this paper proposes a scheduling pool scheduling algorithm based on reuse of jobs. This algorithm is based on the original scheduling pool scheduling algorithm in Spark and can take great advantage of the reusable parts. Experiments show that the new scheduling algorithm realizes reuse of jobs, and improves the execution efficiency of the cluster.
Real-time embedded systems have become widely used in many fields such as control, monitoring and aviation. They perform several tasks under strict time constraints. In such systems, deadline miss may lead to catastro...
详细信息
ISBN:
(纸本)9781509006793
Real-time embedded systems have become widely used in many fields such as control, monitoring and aviation. They perform several tasks under strict time constraints. In such systems, deadline miss may lead to catastrophic results so that all jobs need to be scheduled appropriately to ensure that they meet their deadline times. This paper presents an efficient dynamic scheduling algorithm during run-time to schedule periodic tasks in multiprocessor environments and uniprocessor as well using a dynamic average estimation. Dynamic average estimation refers to changing in different probability distributions when a task is added or removed from them. It is not always available a value of Worst-Case Execution Time (WCET) in many real-time applications such as multimedia where data has a great variation. The proposed approach selects which task or a set of tasks must be picked up for execution. A simulation system was developed to show validation of the proposed approach.
Digital learning in Indonesian rural area faces some problems in delivering Video-on-Demand (VoD) as learning materials because of heterogeneous and limited network. Recently, data-driven overlay network (DONet) appro...
详细信息
ISBN:
(纸本)9781509016204
Digital learning in Indonesian rural area faces some problems in delivering Video-on-Demand (VoD) as learning materials because of heterogeneous and limited network. Recently, data-driven overlay network (DONet) approaches have attracted a lot of attention to solve VoD delivery problems in peer-to-peer based network. This paper presents an enhanced algorithm in overlay-network based digital learning built upon on previous research called CoolStreaming. The new algorithm takes into account bandwidth allocation of each node in scheduling content delivery process. The modified algorithm is then validated by comparing it with the previous algorithm. Validation of the proposed algorithm was based on simulation using OverSim and OMNET++ network simulator. We conducted three different scenarios to compare the proposed algorithm with the previous algorithm. The results show that the proposed algorithm has given better Quality of Service (QoS) performance than previous algorithm in all scenarios. The enhanced algorithm has indicated good quality in the investigated QoS parameters, namely delay and throughput.
In large cloud data center where the virtualization technologies are widely used, a challenging issue is how to efficiently allocate and migrate virtual resources. In this paper, we propose a novel scheduling algorith...
详细信息
ISBN:
(纸本)9781467385152
In large cloud data center where the virtualization technologies are widely used, a challenging issue is how to efficiently allocate and migrate virtual resources. In this paper, we propose a novel scheduling algorithm based on resource overcommitment, as called i-porter. The main goal of i-porter algorithm is to improve the utilizations of heterogeneous physical resources in virtualization environments. Compared to the existing solutions, i-porter has the following advantages: 1) it is a two levels of architecture that can meet the scheduling requirements, whether for virtual machine building or migration;2) it makes the layouts of the virtual machines to be consistent and improves the cost-efficacy of the whole data center. Based on a prototype implementation of i-porter, our evaluation results show that i-porter algorithm performs excellent in resource scheduling and cost savings.
Random distribution of sensor nodes in large scale network leads redundant nodes in the application field. Sensor nodes are with irreplaceable battery in nature, which drains the energy due to repeated collection...
详细信息
Random distribution of sensor nodes in large scale network leads redundant nodes in the application field. Sensor nodes are with irreplaceable battery in nature, which drains the energy due to repeated collection of data and decreases network lifetime. scheduling algorithms are the one way of addressing this issue. In proposed method, an optimized sleep scheduling used to enhance the network lifetime. While using the scheduling algorithm, the target coverage and data collection must be maintained throughout the network. In-network, aggregation method also used to remove the unwanted information in the collected data in level. Modified clustering algorithm highlights three cluster heads in each cluster which are separated by minimum distance between them. The simulation results show the 20% improvement in network lifetime, 25% improvement in throughput and 30% improvement in end to end delay.
On-demand data broadcasting scheduling is an effective wireless data dissemination technique. Existing scheduling algorithms usually have two problems: (1) with the explosive growth of mobile users and real-time indiv...
详细信息
On-demand data broadcasting scheduling is an effective wireless data dissemination technique. Existing scheduling algorithms usually have two problems: (1) with the explosive growth of mobile users and real-time individual requirements, broadcasting systems present a shortage of scalability, dynamics and timeliness (request drop ratio);(2) with the growth of intelligent and entertained application, energy consumption of mobile client cannot be persistent (tuning time). This paper proposes an effective scheduling algorithm LxRxW. It takes into account the number of lost requests during next item broadcasting time, the number of requests and the waiting time. LxRxW can reduce the request drop ratio. At the same time, the algorithm employs a dynamic index strategy to put forward a dynamic adjusting method on the index cycle length (DAIL) to determine the proper index cycle. Extensive experimental results show that the LxRxW algorithm has better performance than other state-of-the-art scheduling algorithms and can significantly reduce the drop ratio of user requests by 40%-50%. The request drop ratio and accessing time of LxRxW with index increase by 1%-2% than LxRxW algorithm without index, but the tuning time decreases by 70%. The index strategy shows that when the index cycle length is less than 20units, it can significantly reduce the average tuning time but when the index cycle length continues increasing, the average tuning time will increase contrarily. DAIL can dynamically determine the length of index cycle. Moreover, it can reach optimal integrated performance of the request drop ratio, the average accessing time and the average tuning time. Copyright (c) 2013 John Wiley & Sons, Ltd.
暂无评论